How to integrate Zoom MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Zoom Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Zoom to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Zoom agent that can schedule a zoom meeting for tomorrow, add a registrant to my next webinar, summarize my last recorded meeting, list participants from yesterday's meeting through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Zoom account through Composio's Zoom MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Zoom
  • Configure an AI agent that can use Zoom as a tool
  • Run a live chat session where you can ask the agent to perform Zoom operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Zoom MCP server, and what's possible with it?

The Zoom MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zoom account. It provides structured and secure access to your meetings, webinars, and usage data, so your agent can schedule meetings, register attendees, retrieve recordings, summarize sessions, and analyze participant engagement on your behalf.

  • Automated meeting scheduling and management: Instruct your agent to create new Zoom meetings, fetch details for upcoming or past meetings, and manage all your session logistics effortlessly.
  • Seamless participant and registrant registration: Have your agent add attendees or registrants to meetings and webinars, handling all required information and permissions automatically.
  • On-demand access to recordings and summaries: Let your agent retrieve meeting recordings or generate AI-powered meeting summaries, making it easy to review or share past sessions.
  • Insightful participant analytics: Ask your agent to fetch detailed lists of past meeting participants or generate daily usage reports, helping you track engagement and attendance trends.
  • Efficient recording and data cleanup: Direct your agent to delete outdated recordings or manage your Zoom storage, keeping your account streamlined and organized.

Supported Tools & Triggers

Tools
Add a meeting registrantThis text guides on creating and customizing a user's registration for a zoom meeting, with a max of 4,999 registrants.
Add a webinar registrantZoom users with a webinar plan can create and manage webinars, broadcasting to up to 10,000 attendees.
Create a meetingEnable zoom meeting creation via user-level apps with "me".
Delete meeting recordingsSummary: to delete all meeting recordings, ensure the user's account has cloud recording enabled.
Get a meetingThe text provides details on api permissions for reading meeting information, categorizing permissions into general and granular scopes, and labels the rate limit as 'light'.
Get a meeting summaryMeeting summary info requires a pro+ host plan, ai companion enabled, excluding e2ee meetings.
Get a webinarAccess zoom webinar details requires pro or higher plan and webinar add-on.
Get daily usage reportThe daily report provides zoom service usage details, like new users, meetings, participants, and minutes per day for a month, requiring a pro plan or higher.
Get meeting recordingsTo download meeting recordings, use `download url`.
Get past meeting participantsApi allows paid users (pro+) to fetch past meeting attendee info, excluding solo participants.
List all recordingsThis text details how to list zoom cloud recordings for a user, notably by using "me" for user-level apps and requiring an oauth token for access.
List archived filesZoom's archiving solution enables administrators to automatically record and archive meeting data to third-party platforms for compliance, needing the meeting and webinar archiving feature enabled.
List devicesThis api lets you list devices.
List meetingsThis zoom api lists a user's scheduled meetings using the `me` value for user-level apps, excluding instant meetings and only showing unexpired ones.
List webinar participantsGet a list of past webinar participants with a pro plan or above plus an add-on.
List webinarsThe api lists all scheduled webinars for zoom users with a webinar plan, using `me` for user-level apps.
Update a meetingTo update a meeting via api, ensure `start time` is future-dated; `recurrence` is needed.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Zoom project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Zoom.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Zoom Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["zoom"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only zoom.
  • The router checks the user's Zoom connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Zoom.
  • This approach keeps things lightweight and lets the agent request Zoom tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Zoom. "
        "Help users perform Zoom operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Zoom and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Zoom operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Zoom.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Zoom and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["zoom"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Zoom. "
        "Help users perform Zoom operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Zoom MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Zoom.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Zoom MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Zoom MCP with Claude Agent SDK

Google ADK

Google ADK

Use Zoom MCP with Google ADK

LangChain

LangChain

Use Zoom MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Zoom MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Zoom MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Zoom MCP with LlamaIndex

CrewAI

CrewAI

Use Zoom MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Zoom MCP?

With a standalone Zoom MCP server, the agents and LLMs can only access a fixed set of Zoom tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Zoom and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Zoom tools.

Can I manage the permissions and scopes for Zoom while using Tool Router?

Yes, absolutely. You can configure which Zoom scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Zoom data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free